Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _money
    -0.08
    ُه
    -0.07
    “What
    -0.06
    orgetown
    -0.06
     Seeder
    -0.06
    "What
    -0.06
    SerializedName
    -0.06
     LaTeX
    -0.06
    �
    -0.06
    Iter
    -0.06
    POSITIVE LOGITS
    (previous
    0.08
    PROTO
    0.07
    δοση
    0.06
    job
    0.06
    基金
    0.06
    olithic
    0.06
    indexed
    0.06
     дол
    0.06
    .unbind
    0.06
     Become
    0.06
    Act Density 0.001%

    No Known Activations